Continuing learning about search evaluation #LLMZoomcamp www.twitch.tv/swillcodes
swillcodes - Twitch
Back learning llms: search eval #llmzoomcamp
www.twitch.tv
July 15, 2026 at 7:24 AM
Continuing learning about search evaluation #LLMZoomcamp www.twitch.tv/swillcodes
Onto module 2 #llmzoomcamp www.twitch.tv/swillcodes?s...
swillcodes - Twitch
Day 8 learning llms #llmzoomcamp
www.twitch.tv
June 22, 2026 at 7:41 AM
Onto module 2 #llmzoomcamp www.twitch.tv/swillcodes?s...
swillcodes - Twitch
Back learning llms: search eval #llmzoomcamp
www.twitch.tv
July 8, 2026 at 7:41 AM
Tuning search parameters #LLMZoomcamp www.twitch.tv/swillcodes
swillcodes - Twitch
Back learning llms: search eval #llmzoomcamp
www.twitch.tv
July 16, 2026 at 7:38 AM
Tuning search parameters #LLMZoomcamp www.twitch.tv/swillcodes
Finishing up module 1 content today! #llmzoomcamp www.twitch.tv/swillcodes?s...
swillcodes - Twitch
Day 7 learning llms #llmzoomcamp
www.twitch.tv
June 17, 2026 at 6:16 AM
Finishing up module 1 content today! #llmzoomcamp www.twitch.tv/swillcodes?s...
We live making progress in module 2, Vector search #llmzoomcamp www.twitch.tv/swillcodes
swillcodes - Twitch
Day 9 learning llms #llmzoomcamp
www.twitch.tv
June 23, 2026 at 7:28 AM
We live making progress in module 2, Vector search #llmzoomcamp www.twitch.tv/swillcodes
Finished Module 3 of the #LLMZoomcamp 🚀
We covered the entire offline evaluation pipeline: from generating a ground truth dataset to assessing performance with metrics like MRR, Hit Rate, and Cosine Similarity, plus the fascinating LLM-as-a-Judge approach.
#LLMZoomcamp #RAG #LLM #Evaluation
We covered the entire offline evaluation pipeline: from generating a ground truth dataset to assessing performance with metrics like MRR, Hit Rate, and Cosine Similarity, plus the fascinating LLM-as-a-Judge approach.
#LLMZoomcamp #RAG #LLM #Evaluation
July 28, 2025 at 11:43 PM
Finished Module 3 of the #LLMZoomcamp 🚀
We covered the entire offline evaluation pipeline: from generating a ground truth dataset to assessing performance with metrics like MRR, Hit Rate, and Cosine Similarity, plus the fascinating LLM-as-a-Judge approach.
#LLMZoomcamp #RAG #LLM #Evaluation
We covered the entire offline evaluation pipeline: from generating a ground truth dataset to assessing performance with metrics like MRR, Hit Rate, and Cosine Similarity, plus the fascinating LLM-as-a-Judge approach.
#LLMZoomcamp #RAG #LLM #Evaluation
Continuing with vector search today #llmzoomcamp www.twitch.tv/swillcodes
swillcodes - Twitch
Day 10 learning llms #llmzoomcamp
www.twitch.tv
June 24, 2026 at 6:31 AM
Continuing with vector search today #llmzoomcamp www.twitch.tv/swillcodes
Challenges in LLM evaluation include data contamination, outdated benchmarks, and the inherent subjectivity of human judgments. Addressing these requires ongoing innovation. #AIChallenges #LLMEvaluation #llmzoomcamp
August 11, 2025 at 10:51 PM
Challenges in LLM evaluation include data contamination, outdated benchmarks, and the inherent subjectivity of human judgments. Addressing these requires ongoing innovation. #AIChallenges #LLMEvaluation #llmzoomcamp
🚀 Just completed my #DataTalksClub LLM Zoomcamp project: DocuMind - an end-to-end RAG system for technical documents!
Built with Google Gemini, LangChain, ChromaDB & Streamlit.
Let me share what I learned... 🧵
#LLMZOOMCAMP #BuildInPublic #AI
Built with Google Gemini, LangChain, ChromaDB & Streamlit.
Let me share what I learned... 🧵
#LLMZOOMCAMP #BuildInPublic #AI
October 20, 2025 at 6:34 AM
🚀 Just completed my #DataTalksClub LLM Zoomcamp project: DocuMind - an end-to-end RAG system for technical documents!
Built with Google Gemini, LangChain, ChromaDB & Streamlit.
Let me share what I learned... 🧵
#LLMZOOMCAMP #BuildInPublic #AI
Built with Google Gemini, LangChain, ChromaDB & Streamlit.
Let me share what I learned... 🧵
#LLMZOOMCAMP #BuildInPublic #AI
Starting Project 2 of #llmzoomcamp. I’m keeping the same cyber focus, but shifting from an organisation-guidance angle to something more practitioner-oriented, where retrieval has to be precise, grounded, and useful in real workflows.
August 12, 2026 at 1:36 AM
Starting Project 2 of #llmzoomcamp. I’m keeping the same cyber focus, but shifting from an organisation-guidance angle to something more practitioner-oriented, where retrieval has to be precise, grounded, and useful in real workflows.
Week 2 completed for ##LLM DataZoomCamp.
I can now have dinner table conversations on embedding, vector databases and vector searches. I dont mind the looks from family members. Week 3 Lets go
@qdrant.bsky.social
#llmzoomcamp
I can now have dinner table conversations on embedding, vector databases and vector searches. I dont mind the looks from family members. Week 3 Lets go
@qdrant.bsky.social
#llmzoomcamp
June 23, 2025 at 5:34 AM
Week 2 completed for ##LLM DataZoomCamp.
I can now have dinner table conversations on embedding, vector databases and vector searches. I dont mind the looks from family members. Week 3 Lets go
@qdrant.bsky.social
#llmzoomcamp
I can now have dinner table conversations on embedding, vector databases and vector searches. I dont mind the looks from family members. Week 3 Lets go
@qdrant.bsky.social
#llmzoomcamp
💡 WRAP-UP
Built a complete RAG system with:
✅ Optimized retrieval (k=3, 86.67% precision)
✅ Evaluated prompts (8.0/10 quality)
✅ Real-time monitoring (7 charts)
✅ Full Docker deployment
✅ Hallucination prevention
#LLMZOOMCAMP #BuildInPublic
Built a complete RAG system with:
✅ Optimized retrieval (k=3, 86.67% precision)
✅ Evaluated prompts (8.0/10 quality)
✅ Real-time monitoring (7 charts)
✅ Full Docker deployment
✅ Hallucination prevention
#LLMZOOMCAMP #BuildInPublic
October 20, 2025 at 6:48 AM
💡 WRAP-UP
Built a complete RAG system with:
✅ Optimized retrieval (k=3, 86.67% precision)
✅ Evaluated prompts (8.0/10 quality)
✅ Real-time monitoring (7 charts)
✅ Full Docker deployment
✅ Hallucination prevention
#LLMZOOMCAMP #BuildInPublic
Built a complete RAG system with:
✅ Optimized retrieval (k=3, 86.67% precision)
✅ Evaluated prompts (8.0/10 quality)
✅ Real-time monitoring (7 charts)
✅ Full Docker deployment
✅ Hallucination prevention
#LLMZOOMCAMP #BuildInPublic
Study time! #llmzoomcamp www.twitch.tv/swillcodes
swillcodes - Twitch
Exploring and improving my code one day at a time. Mostly data science.
www.twitch.tv
June 10, 2026 at 5:52 AM
Study time! #llmzoomcamp www.twitch.tv/swillcodes
📚 Completed the Agents module of #LLMZoomcamp! From basic function descriptions to full MCP implementations. Ready to build AI agents that don't just talk, but actually DO things in the real world! 🎯
Next stop: Production-ready AI agents! 🚀
#LLMZoomcamp #AIAgents #MachineLearning
Next stop: Production-ready AI agents! 🚀
#LLMZoomcamp #AIAgents #MachineLearning
July 16, 2025 at 5:21 PM
📚 Completed the Agents module of #LLMZoomcamp! From basic function descriptions to full MCP implementations. Ready to build AI agents that don't just talk, but actually DO things in the real world! 🎯
Next stop: Production-ready AI agents! 🚀
#LLMZoomcamp #AIAgents #MachineLearning
Next stop: Production-ready AI agents! 🚀
#LLMZoomcamp #AIAgents #MachineLearning
Completed the Module Homework of #llmzoomcamp! ✅
🔹 Installed and used dlt with Qdrant support
🔹 Loaded FAQ data into a Qdrant vector database
🔹 Created and ran a dlt pipeline for data ingestion
🔹 Explored embedding models used during data insertion
Hands-on, practical learning! 📊 #llmzoomcamp
🔹 Installed and used dlt with Qdrant support
🔹 Loaded FAQ data into a Qdrant vector database
🔹 Created and ran a dlt pipeline for data ingestion
🔹 Explored embedding models used during data insertion
Hands-on, practical learning! 📊 #llmzoomcamp
July 10, 2025 at 8:28 PM
Completed the Module Homework of #llmzoomcamp! ✅
🔹 Installed and used dlt with Qdrant support
🔹 Loaded FAQ data into a Qdrant vector database
🔹 Created and ran a dlt pipeline for data ingestion
🔹 Explored embedding models used during data insertion
Hands-on, practical learning! 📊 #llmzoomcamp
🔹 Installed and used dlt with Qdrant support
🔹 Loaded FAQ data into a Qdrant vector database
🔹 Created and ran a dlt pipeline for data ingestion
🔹 Explored embedding models used during data insertion
Hands-on, practical learning! 📊 #llmzoomcamp
Loaded Zoomcamp FAQ data straight into Qdrant with a single dlt pipeline. 948 rows indexed and ready for search in minutes! #LLMZOOMCAMP
July 11, 2025 at 6:25 PM
Loaded Zoomcamp FAQ data straight into Qdrant with a single dlt pipeline. 948 rows indexed and ready for search in minutes! #LLMZOOMCAMP
🛠️ TECH STACK
• LLM: Google Gemini 2.5 Pro
• Embeddings: text-embedding-004
• Vector DB: ChromaDB
• Framework: LangChain
• UI: Streamlit
• Container: Docker
All production-ready with monitoring!
#LLMZOOMCAMP #TechStack
• LLM: Google Gemini 2.5 Pro
• Embeddings: text-embedding-004
• Vector DB: ChromaDB
• Framework: LangChain
• UI: Streamlit
• Container: Docker
All production-ready with monitoring!
#LLMZOOMCAMP #TechStack
October 20, 2025 at 6:36 AM
🛠️ TECH STACK
• LLM: Google Gemini 2.5 Pro
• Embeddings: text-embedding-004
• Vector DB: ChromaDB
• Framework: LangChain
• UI: Streamlit
• Container: Docker
All production-ready with monitoring!
#LLMZOOMCAMP #TechStack
• LLM: Google Gemini 2.5 Pro
• Embeddings: text-embedding-004
• Vector DB: ChromaDB
• Framework: LangChain
• UI: Streamlit
• Container: Docker
All production-ready with monitoring!
#LLMZOOMCAMP #TechStack
🛡️ PREVENTING HALLUCINATIONS
Tested with out-of-scope questions.
System correctly says "I cannot tell you based on the provided context" instead of making things up.
Honesty > Confidence
#LLMZOOMCAMP #AIEthics
Tested with out-of-scope questions.
System correctly says "I cannot tell you based on the provided context" instead of making things up.
Honesty > Confidence
#LLMZOOMCAMP #AIEthics
October 20, 2025 at 6:44 AM
🛡️ PREVENTING HALLUCINATIONS
Tested with out-of-scope questions.
System correctly says "I cannot tell you based on the provided context" instead of making things up.
Honesty > Confidence
#LLMZOOMCAMP #AIEthics
Tested with out-of-scope questions.
System correctly says "I cannot tell you based on the provided context" instead of making things up.
Honesty > Confidence
#LLMZOOMCAMP #AIEthics
Finished the homework with ElasticSearch working smoothly. From indexing to querying and dynamic prompt generation—really getting the hang of LLM-based workflows! 🚀💡
#LLMZoomcamp #DataTalksClub
#LLMZoomcamp #DataTalksClub
June 16, 2025 at 11:21 PM
Finished the homework with ElasticSearch working smoothly. From indexing to querying and dynamic prompt generation—really getting the hang of LLM-based workflows! 🚀💡
#LLMZoomcamp #DataTalksClub
#LLMZoomcamp #DataTalksClub
